Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sorting descending order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     up
    0.78
    ruption
    0.77
    up
    0.74
    Alphabet
    0.72
     जनवरी
    0.70
     alphabetically
    0.68
     Tetrahedron
    0.67
     weak
    0.67
    фра
    0.67
    ورش
    0.66
    POSITIVE LOGITS
     Desc
    1.94
     descended
    1.82
    desc
    1.76
     descending
    1.74
     desc
    1.73
    Desc
    1.73
     descend
    1.72
    Descending
    1.60
     DESC
    1.58
     descends
    1.55
    Act Density 0.029%

    No Known Activations